AGIdex
SUB-CAPABILITY · SOCIAL INTELLIGENCE

Empathy

30%
vs. HUMAN BASELINE = 100
UnsolvedConf · Low

Scoring rubric

0–20
Early research
20–40
Narrow benchmark competence
40–60
Strong benchmark · reliability gaps
60–80
Human-competitive in common scenarios
80–100
Comparable to typical skilled adult
100+
Reliably exceeds typical human baseline

Score vs. baseline

Trend · Last 12 months
12mo ago   %
6mo ago   %
Today   %
Δ 12mo   +0

What this measures

Human baseline

Recognize and appropriately respond to others' emotional states in conversation.

Human frontier

Genuine emotional attunement sustained across context — not pattern-matched scripts.

Current state

What works

Surface affective recognition; appropriate response selection in structured dialogue.

Key gaps

Whether models experience anything analogous to empathy is not measurable — scores reflect behavioral proxies only.

Evidence

0 sources
TechnologyQualitySourceScore vs. baselineScore
No evidence records yet.